Welcome to Francis Academic Press

Academic Journal of Computing & Information Science, 2024, 7(3); doi: 10.25236/AJCIS.2024.070306.

Research on Deep Learning-based Image Semantic Segmentation and Scene Understanding


Liu Fenfen1, Zhu Zimin2

Corresponding Author:
Liu Fenfen

1Xi'an Peihua University, Xi'an, 710125, China

2Northeast Forestry University, Harbin, 150006, China


This research investigates the intricate domain of deep learning-based image semantic segmentation and scene understanding. The fundamentals of image semantic segmentation are explored, tracing the evolution from traditional methods to the emergence of deep learning techniques. Deep learning architectures for semantic segmentation are thoroughly reviewed, encompassing popular CNNs architectures like U-Net, FCNs, and SegNet, along with their respective advantages and drawbacks. Furthermore, recent advancements and novel architectures aimed at improving segmentation performance are scrutinized, highlighting the integration of attention mechanisms and the development of encoder-decoder architectures with skip connections. Datasets and Evaluation Metrics crucial for benchmarking and assessing the efficacy of semantic segmentation models are also examined. By addressing these facets comprehensively, this research aims to contribute to the ongoing advancement of deep learning methodologies in image analysis, fostering enhanced scene understanding and paving the way for more robust computer vision systems.


Deep learning, Image semantic segmentation, Scene understanding, Convolutional neural networks, Evaluation metrics

Cite This Paper

Liu Fenfen, Zhu Zimin. Research on Deep Learning-based Image Semantic Segmentation and Scene Understanding. Academic Journal of Computing & Information Science (2024), Vol. 7, Issue 3: 43-48. https://doi.org/10.25236/AJCIS.2024.070306.


[1] Li, X., Zhao, Z., & Wang, Q. (2021). ABSSNet: Attention-based spatial segmentation network for traffic scene understanding. IEEE transactions on cybernetics, 52(9), 9352-9362.

[2] Liu, X., Neuyen, M., & Yan, W. Q. (2020). Vehicle-related scene understanding using deep learning. In Pattern Recognition: ACPR 2019 Workshops, Auckland, New Zealand, November 26, 2019, Proceedings 5 (pp. 61-73). Springer Singapore.

[3] Zamani, V., Taghaddos, H., Gholipour, Y., & Pourreza, H. (2022). Deep semantic segmentation for visual scene understanding of soil types. Automation in Construction, 140, 104342.

[4] Emek Soylu, B., Guzel, M. S., Bostanci, G. E., Ekinci, F., Asuroglu, T., & Acici, K. (2023). Deep-learning-based approaches for semantic segmentation of natural scene images: A review. Electronics, 12(12), 2730.

[5] Muhammad, K., Hussain, T., Ullah, H., Del Ser, J., Rezaei, M., Kumar, N., ... & de Albuquerque, V. H. C. (2022). Vision-based semantic segmentation in scene understanding for autonomous driving: Recent achievements, challenges, and outlooks. IEEE Transactions on Intelligent Transportation Systems, 23(12), 22694-22715.

[6] Guo, Z., Huang, Y., Hu, X., Wei, H., & Zhao, B. (2021). A survey on deep learning based approaches for scene understanding in autonomous driving. Electronics, 10(4), 471.

[7] Pereira, R., Barros, T., Garrote, L., Lopes, A., & Nunes, U. J. (2024). A deep learning-based global and segmentation-based semantic feature fusion approach for indoor scene classification. Pattern Recognition Letters, 179, 24-30.